© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5761
    Prev
    Next
    INDEX
    Explanations

    terms related to disease and death

    oai_token-act-pair · gemini-2.0-flash

    illnesses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.68
     виправивши
    -0.57
    ngrx
    -0.56
    DebuggerNonUser
    -0.56
     Erişim
    -0.49
    Personendaten
    -0.49
    ngOn
    -0.49
    ättern
    -0.48
    igshid
    -0.48
     مشين
    -0.47
    POSITIVE LOGITS
     circulaire
    0.51
    +#+#
    0.50
    hoodie
    0.48
    讐
    0.48
     Smoke
    0.47
     الوطنيه
    0.47
     Mone
    0.47
    Composable
    0.47
     Fug
    0.47
    mybatisplus
    0.47
    Activations Density 4.252%

    No Known Activations